Reducing DRAM Refresh Overheads with Refresh-Access Parallelism

TL;DR

This paper introduces refresh-access parallelism techniques, DARP and SARP, to reduce DRAM refresh overheads by enabling parallel refreshes and accesses, significantly improving performance and energy efficiency especially in high-density DRAM systems.

Contribution

The paper proposes two novel mechanisms, DARP and SARP, that enable parallel refreshes and accesses within DRAM, addressing limitations of traditional per-bank refresh methods.

Findings

Performance improvements over state-of-the-art policies

Energy efficiency gains in various workloads

Benefits increase with higher DRAM density

Abstract

This article summarizes the idea of "refresh-access parallelism," which was published in HPCA 2014, and examines the work's significance and future potential. The overarching objective of our HPCA 2014 paper is to reduce the significant negative performance impact of DRAM refresh with intelligent memory controller mechanisms. To mitigate the negative performance impact of DRAM refresh, our HPCA 2014 paper proposes two complementary mechanisms, DARP (Dynamic Access Refresh Parallelization) and SARP (Subarray Access Refresh Parallelization). The goal is to address the drawbacks of state-of-the-art per-bank refresh mechanism by building more efficient techniques to parallelize refreshes and accesses within DRAM. First, instead of issuing per-bank refreshes in a round-robin order, as it is done today, DARP issues per-bank refreshes to idle banks in an out-of-order manner. Furthermore, DARP proactively schedules refreshes during intervals when a batch of writes are draining to DRAM. Second, SARP exploits the existence of mostly-independent subarrays within a bank. With minor modifications to DRAM organization, it allows a bank to serve memory accesses to an idle subarray while another subarray is being refreshed. Our extensive evaluations on a wide variety of workloads and systems show that our mechanisms improve system performance (and energy efficiency) compared to three state-of-the-art refresh policies, and their performance bene ts increase as DRAM density increases.